INDEX

Explanations

words related to functions, operations, or processes within contexts like databases, health care, and scientific research

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Follows prepositions or conjunctions

np_acts-logits-general · gemini-2.0-flash

function of, host ranges, factors of

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 المعيارى

-0.88

 OnInit

-0.48

ronpa

-0.47

Становништво

-0.46

derung

-0.46

Nationalité

-0.45

يميديا

-0.43

JspWriter

-0.43

pinMode

-0.43

 esternos

-0.42

POSITIVE LOGITS

">//

0.47

SourceChecksum

0.40

 wireType

0.40

tagHelperRunner

0.39

帖最后由

0.39

StylePriority

0.39

 respectively

0.37

 alike

0.35

KURZBESCHREIBUNG

0.35

LEGGI

0.34

Activations Density 0.869%

words related to functions, operations, or processes within contexts like databases, health care, and scientific research

Follows prepositions or conjunctions

function of, host ranges, factors of

No Comments

No Known Activations